Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 346
    Prev
    Next
    INDEX
    Explanations

    the references to sourcing or results derived from specific studies or datasets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    netbeans
    -0.46
     PFS
    -0.43
    pyplot
    -0.43
    atchi
    -0.43
    ombe
    -0.43
     CAC
    -0.42
    CAC
    -0.42
    TTC
    -0.42
     NRC
    -0.41
    getMessage
    -0.41
    POSITIVE LOGITS
    PerformLayout
    1.04
    XmlAccessorType
    0.95
    ConstraintMaker
    0.93
     AssemblyTitle
    0.92
    RegressionTest
    0.87
    DotNetBar
    0.84
    GEBURTS
    0.84
     <=",
    0.84
    +#+#
    0.83
    DllImport
    0.83
    Activations Density 0.588%

    No Known Activations